© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24439
    Prev
    Next
    INDEX
    Explanations

    quantities and ingredients in a cooking recipe

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to cooking ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specificity
    -0.69
    icist
    -0.67
     ancestor
    -0.65
     Investigative
    -0.64
     fallacy
    -0.62
    omaly
    -0.62
    athe
    -0.61
    attr
    -0.60
     successor
    -0.57
     deletion
    -0.57
    POSITIVE LOGITS
     ounces
    1.45
     tablespoons
    1.42
     cloves
    1.37
     cups
    1.32
     oz
    1.27
     tbsp
    1.23
     servings
    1.22
     teaspoons
    1.22
     slices
    1.19
     grams
    1.18
    Activations Density 0.068%

    No Known Activations